Technology

Since the 1990s, successful investing has required the integration of cross-market analysis with traditional technical analysis. Analysis of individual markets must now give way to a broader analytical perspective that takes into account the non-linear relationships between different financial markets. Neural networks are a great tool for synergistic analysis. They can combine different types of data in an analysis and find hidden patterns and complex relationships between markets. Neural networks do a great job of processing large amounts of market data.

Input data: technical, fundamental, and inter-market
Backpropagation error		INPUT HIDDEN LAYER OUTPUT
	Output data: price, direction, or signal

A backpropagation network consists of an input layer, one or more hidden layers, and an output layer. The input layer consists of a number of neurons equal to the number of (independent) input variables. The output layer contains one neuron for each (dependent) predicted output variable. The neurons of the hidden layer are connected to both the input and the output layers. The connections of the layers are usually complete, which means that each neuron of a given layer is connected to all neurons of the neighboring layer. The values assigned to each neuron of the input layer are passed to all neurons of the hidden layer. Here they are multiplied by the appropriate weight, summed and processed by a transfer function to obtain the output. The output data from the first hidden layer is passed to the next hidden layer or, in networks with one hidden layer, to the output layer. The output layer outputs the prediction made by the network.